Sampling Phrase Tables for the Moses Statistical Machine Translation System

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

The idea of virtual phrase tables for statistical machine translation (SMT) that construct phrase table entries on demand by sampling a fully indexed bitext was first proposed ten years ago by Callison-Burch et al. (2005). However, until recently (Germann, 2014) no working and practical implementation of this approach was available in the Moses SMT system. We describe and evaluate this implementation in more detail. Sampling phrase tables are much faster to build and are competitive with conventional phrase tables in terms of translation quality and speed.
Original languageEnglish
Pages (from-to)39-50
Number of pages12
JournalPrague Bulletin of Mathematical Linguistics
Issue number1
Publication statusPublished - 2015


Dive into the research topics of 'Sampling Phrase Tables for the Moses Statistical Machine Translation System'. Together they form a unique fingerprint.

Cite this